PopGenAdapt: Semi-Supervised Domain Adaptation for Genotype-to-Phenotype Prediction in Underrepresented Populations.

The lack of diversity in genomic datasets, currently skewed towards individuals of European ancestry, presents a challenge in developing inclusive biomedical models. The scarcity of such data is particularly evident in labeled datasets that include genomic data linked to electronic health records. To address this gap, this paper presents PopGenAdapt, a genotype-to-phenotype prediction model which adopts semi-supervised domain adaptation (SSDA) techniques originally proposed for computer vision. PopGenAdapt is designed to leverage the substantial labeled data available from individuals of European ancestry, as well as the limited labeled and the larger amount of unlabeled data from currently underrepresented populations. The method is evaluated in underrepresented populations from Nigeria, Sri Lanka, and Hawaii for the prediction of several disease outcomes. The results suggest a significant improvement in the performance of genotype-to-phenotype models for these populations over state-of-the-art supervised learning methods, setting SSDA as a promising strategy for creating more inclusive machine learning models in biomedical research.Our code is available at https://github.com/AI-sandbox/PopGenAdapt.

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations.

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

Session Introduction: Overcoming health disparities in precision medicine.

The following sections are included:OverviewDealing with the lack of diversity in current research datasetsDevelopment of fair machine learning algorithmsRace, genetic ancestry, and population structureConclusionAcknowledgments.

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations.

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

PopGenAdapt: Semi-Supervised Domain Adaptation for Genotype-to-Phenotype Prediction in Underrepresented Populations.

The lack of diversity in genomic datasets, currently skewed towards individuals of European ancestry, presents a challenge in developing inclusive biomedical models. The scarcity of such data is particularly evident in labeled datasets that include genomic data linked to electronic health records. To address this gap, this paper presents PopGenAdapt, a genotype-to-phenotype prediction model which adopts semi-supervised domain adaptation (SSDA) techniques originally proposed for computer vision. PopGenAdapt is designed to leverage the substantial labeled data available from individuals of European ancestry, as well as the limited labeled and the larger amount of unlabeled data from currently underrepresented populations. The method is evaluated in underrepresented populations from Nigeria, Sri Lanka, and Hawaii for the prediction of several disease outcomes. The results suggest a significant improvement in the performance of genotype-to-phenotype models for these populations over state-of-the-art supervised learning methods, setting SSDA as a promising strategy for creating more inclusive machine learning models in biomedical research.

Mexican Biobank advances population and medical genomics of diverse ancestries.

Latin America continues to be severely underrepresented in genomics research, and fine-scale genetic histories and complex trait architectures remain hidden owing to insufficient data1. To fill this gap, the Mexican Biobank project genotyped 6,057 individuals from 898 rural and urban localities across all 32 states in Mexico at a resolution of 1.8 million genome-wide markers with linked complex trait and disease information creating a valuable nationwide genotype-phenotype database. Here, using ancestry deconvolution and inference of identity-by-descent segments, we inferred ancestral population sizes across Mesoamerican regions over time, unravelling Indigenous, colonial and postcolonial demographic dynamics2-6. We observed variation in runs of homozygosity among genomic regions with different ancestries reflecting distinct demographic histories and, in turn, different distributions of rare deleterious variants. We conducted genome-wide association studies (GWAS) for 22 complex traits and found that several traits are better predicted using the Mexican Biobank GWAS compared to the UK Biobank GWAS7,8. We identified genetic and environmental factors associating with trait variation, such as the length of the genome in runs of homozygosity as a predictor for body mass index, triglycerides, glucose and height. This study provides insights into the genetic histories of individuals in Mexico and dissects their complex trait architectures, both crucial for making precision and preventive medicine initiatives accessible worldwide.

Neural ADMIXTURE for rapid genomic clustering.

Characterizing the genetic structure of large cohorts has become increasingly important as genetic studies extend to massive, increasingly diverse biobanks. Popular methods decompose individual genomes into fractional cluster assignments with each cluster representing a vector of DNA variant frequencies. However, with rapidly increasing biobank sizes, these methods have become computationally intractable. Here we present Neural ADMIXTURE, a neural network autoencoder that follows the same modeling assumptions as the current standard algorithm, ADMIXTURE, while reducing the compute time by orders of magnitude surpassing even the fastest alternatives. One month of continuous compute using ADMIXTURE can be reduced to just hours with Neural ADMIXTURE. A multi-head approach allows Neural ADMIXTURE to offer even further acceleration by calculating multiple cluster numbers in a single run. Furthermore, the models can be stored, allowing cluster assignment to be performed on new data in linear time without needing to share the training samples.

Demographic history and genetic structure in pre-Hispanic Central Mexico.

Aridoamerica and Mesoamerica are two distinct cultural areas in northern and central Mexico, respectively, that hosted numerous pre-Hispanic civilizations between 2500 BCE and 1521 CE. The division between these regions shifted southward because of severe droughts ~1100 years ago, which allegedly drove a population replacement in central Mexico by Aridoamerican peoples. In this study, we present shotgun genome-wide data from 12 individuals and 27 mitochondrial genomes from eight pre-Hispanic archaeological sites across Mexico, including two at the shifting border of Aridoamerica and Mesoamerica. We find population continuity that spans the climate change episode and a broad preservation of the genetic structure across present-day Mexico for the past 2300 years. Lastly, we identify a contribution to pre-Hispanic populations of northern and central Mexico from two ancient unsampled "ghost" populations.

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research.

INTRODUCTION: A major challenge to enabling precision health at a global scale is the bias between those who enroll in state sponsored genomic research and those suffering from chronic disease. More than 30 million people have been genotyped by direct-to-consumer (DTC) companies such as 23andMe, Ancestry DNA, and MyHeritage, providing a potential mechanism for democratizing access to medical interventions and thus catalyzing improvements in patient outcomes as the cost of data acquisition drops. However, much of these data are sequestered in the initial provider network, without the ability for the scientific community to either access or validate. Here, we present a novel geno-pheno platform that integrates heterogeneous data sources and applies learnings to common chronic disease conditions including Type 2 diabetes (T2D) and hypertension. METHODS: We collected genotyped data from a novel DTC platform where participants upload their genotype data files and were invited to answer general health questionnaires regarding cardiometabolic traits over a period of 6 months. Quality control, imputation, and genome-wide association studies were performed on this dataset, and polygenic risk scores were built in a case-control setting using the BASIL algorithm. RESULTS: We collected data on N = 4,550 (389 cases / 4,161 controls) who reported being affected or previously affected for T2D and N = 4,528 (1,027 cases / 3,501 controls) for hypertension. We identified 164 out of 272 variants showing identical effect direction to previously reported genome-significant findings in Europeans. Performance metric of the PRS models was AUC = 0.68, which is comparable to previously published PRS models obtained with larger datasets including clinical biomarkers. DISCUSSION: DTC platforms have the potential of inverting research models of genome sequencing and phenotypic data acquisition. Quality control (QC) mechanisms proved to successfully enable traditional GWAS and PRS analyses. The direct participation of individuals has shown the potential to generate rich datasets enabling the creation of PRS cardiometabolic models. More importantly, federated learning of PRS from reuse of DTC data provides a mechanism for scaling precision health care delivery beyond the small number of countries who can afford to finance these efforts directly. CONCLUSIONS: The genetics of T2D and hypertension have been studied extensively in controlled datasets, and various polygenic risk scores (PRS) have been developed. We developed predictive tools for both phenotypes trained with heterogeneous genotypic and phenotypic data generated outside of the clinical environment and show that our methods can recapitulate prior findings with fidelity. From these observations, we conclude that it is possible to leverage DTC genetic repositories to identify individuals at risk of debilitating diseases based on their unique genetic landscape so that informed, timely clinical interventions can be incorporated.

Predicting Dog Phenotypes from Genotypes.

We analyze dog genotypes (i.e., positions of dog DNA sequences that often vary between different dogs) in order to predict the corresponding phenotypes (i.e., unique observed characteristics). More specifically, given chromosome data from a dog, we aim to predict the breed, height, and weight. We explore a variety of linear and non-linear classification and regression techniques to accomplish these three tasks. We also investigate the use of a neural network (both in linear and non-linear modes) for breed classification and compare the performance to traditional statistical methods. We show that linear methods generally outperform or match the performance of non-linear methods for breed classification. However, we show that the reverse is true for height and weight regression. Finally, we evaluate the results of all of these methods based on the number of input features used in the analysis. We conduct experiments using different fractions of the full genomic sequences, resulting in input sequences ranging from 20 SNPs to ∼200k SNPs. In doing so, we explore the impact of using a very limited number of SNPs for prediction. Our experiments demonstrate that these phenotypes in dogs can be predicted with as few as 0.5% of randomly selected SNPs (i.e., 992 SNPs) and that dog breeds can be classified with 50% balanced accuracy with as few as 0.02% SNPs (i.e., 40 SNPs).

SALAI-Net: species-agnostic local ancestry inference network.

MOTIVATION: Local ancestry inference (LAI) is the high resolution prediction of ancestry labels along a DNA sequence. LAI is important in the study of human history and migrations, and it is beginning to play a role in precision medicine applications including ancestry-adjusted genome-wide association studies (GWASs) and polygenic risk scores (PRSs). Existing LAI models do not generalize well between species, chromosomes or even ancestry groups, requiring re-training for each different setting. Furthermore, such methods can lack interpretability, which is an important element in each of these applications. RESULTS: We present SALAI-Net, a portable statistical LAI method that can be applied on any set of species and ancestries (species-agnostic), requiring only haplotype data and no other biological parameters. Inspired by identity by descent methods, SALAI-Net estimates population labels for each segment of DNA by performing a reference matching approach, which leads to an interpretable and fast technique. We benchmark our models on whole-genome data of humans and we test these models' ability to generalize to dog breeds when trained on human data. SALAI-Net outperforms previous methods in terms of balanced accuracy, while generalizing between different settings, species and datasets. Moreover, it is up to two orders of magnitude faster and uses considerably less RAM memory than competing methods. AVAILABILITY AND IMPLEMENTATION: We provide an open source implementation and links to publicly available data at github.com/AI-sandbox/SALAI-Net. Data is publicly available as follows: https://www.internationalgenome.org (1000 Genomes), https://www.simonsfoundation.org/simons-genome-diversity-project (Simons Genome Diversity Project), https://www.sanger.ac.uk/resources/downloads/human/hapmap3.html (HapMap), ftp://ngs.sanger.ac.uk/production/hgdp/hgdp_wgs.20190516 (Human Genome Diversity Project) and https://www.ncbi.nlm.nih.gov/bioproject/PRJNA448733 (Canid genomes). SUPPLEMENTARY INFORMATION: Supplementary data are available from Bioinformatics online.

Generative Moment Matching Networks for Genotype Simulation.

The generation of synthetic genomic sequences using neural networks has potential to ameliorate privacy and data sharing concerns and to mitigate potential bias within datasets due to under-representation of some population groups. However, there is not a consensus on which architectures, training procedures, and evaluation metrics should be used when simulating single nucleotide polymorphism (SNP) sequences with neural networks. In this paper, we explore the use of Generative Moment Matching Networks (GMMNs) for SNP simulation, we present some architectural and procedural changes to properly train the networks, and we introduce an evaluation scheme to qualitatively and quantitatively assess the quality of the simulated sequences.

Deconvoluting complex correlates of COVID-19 severity with a multi-omic pandemic tracking strategy.

The SARS-CoV-2 pandemic has differentially impacted populations across race and ethnicity. A multi-omic approach represents a powerful tool to examine risk across multi-ancestry genomes. We leverage a pandemic tracking strategy in which we sequence viral and host genomes and transcriptomes from nasopharyngeal swabs of 1049 individuals (736 SARS-CoV-2 positive and 313 SARS-CoV-2 negative) and integrate them with digital phenotypes from electronic health records from a diverse catchment area in Northern California. Genome-wide association disaggregated by admixture mapping reveals novel COVID-19-severity-associated regions containing previously reported markers of neurologic, pulmonary and viral disease susceptibility. Phylodynamic tracking of consensus viral genomes reveals no association with disease severity or inferred ancestry. Summary data from multiomic investigation reveals metagenomic and HLA associations with severe COVID-19. The wealth of data available from residual nasopharyngeal swabs in combination with clinical data abstracted automatically at scale highlights a powerful strategy for pandemic tracking, and reveals distinct epidemiologic, genetic, and biological associations for those at the highest risk.

Archetypal Analysis for population genetics.

The estimation of genetic clusters using genomic data has application from genome-wide association studies (GWAS) to demographic history to polygenic risk scores (PRS) and is expected to play an important role in the analyses of increasingly diverse, large-scale cohorts. However, existing methods are computationally-intensive, prohibitively so in the case of nationwide biobanks. Here we explore Archetypal Analysis as an efficient, unsupervised approach for identifying genetic clusters and for associating individuals with them. Such unsupervised approaches help avoid conflating socially constructed ethnic labels with genetic clusters by eliminating the need for exogenous training labels. We show that Archetypal Analysis yields similar cluster structure to existing unsupervised methods such as ADMIXTURE and provides interpretative advantages. More importantly, we show that since Archetypal Analysis can be used with lower-dimensional representations of genetic data, significant reductions in computational time and memory requirements are possible. When Archetypal Analysis is run in such a fashion, it takes several orders of magnitude less compute time than the current standard, ADMIXTURE. Finally, we demonstrate uses ranging across datasets from humans to canids.

Ancient DNA reveals five streams of migration into Micronesia and matrilocality in early Pacific seafarers.

Micronesia began to be peopled earlier than other parts of Remote Oceania, but the origins of its inhabitants remain unclear. We generated genome-wide data from 164 ancient and 112 modern individuals. Analysis reveals five migratory streams into Micronesia. Three are East Asian related, one is Polynesian, and a fifth is a Papuan source related to mainland New Guineans that is different from the New Britain-related Papuan source for southwest Pacific populations but is similarly derived from male migrants ~2500 to 2000 years ago. People of the Mariana Archipelago may derive all of their precolonial ancestry from East Asian sources, making them the only Remote Oceanians without Papuan ancestry. Female-inherited mitochondrial DNA was highly differentiated across early Remote Oceanian communities but homogeneous within, implying matrilocal practices whereby women almost never raised their children in communities different from the ones in which they grew up.

Opportunities and challenges for the use of common controls in sequencing studies.

Genome-wide association studies using large-scale genome and exome sequencing data have become increasingly valuable in identifying associations between genetic variants and disease, transforming basic research and translational medicine. However, this progress has not been equally shared across all people and conditions, in part due to limited resources. Leveraging publicly available sequencing data as external common controls, rather than sequencing new controls for every study, can better allocate resources by augmenting control sample sizes or providing controls where none existed. However, common control studies must be carefully planned and executed as even small differences in sample ascertainment and processing can result in substantial bias. Here, we discuss challenges and opportunities for the robust use of common controls in high-throughput sequencing studies, including study design, quality control and statistical approaches. Thoughtful generation and use of large and valuable genetic sequencing data sets will enable investigation of a broader and more representative set of conditions, environments and genetic ancestries than otherwise possible.

The genetic legacy of the Manila galleon trade in Mexico.

The population of Mexico has a considerable genetic substructure due to both its pre-Columbian diversity and due to genetic admixture from post-Columbian trans-oceanic migrations. The latter primarily originated in Europe and Africa, but also, to a lesser extent, in Asia. We analyze previously understudied genetic connections between Asia and Mexico to infer the timing and source of this genetic ancestry in Mexico. We identify the predominant origin within Southeast Asia-specifically western Indonesian and non-Negrito Filipino sources-and we date its arrival in Mexico to approximately 13 generations ago (1620 CE). This points to a genetic legacy from the seventeenth century Manila galleon trade between the colonial Spanish Philippines and the Pacific port of Acapulco. Indeed, within Mexico we observe the highest level of this trans-Pacific ancestry in Acapulco, located in the state of Guerrero. This colonial Spanish trade route from East Asia to Europe was centred on Mexico and appears in historical records, but its legacy has been largely ignored. Identities and stories were suppressed due to slavery, assimilation of the immigrants as 'Indios' and incomplete historical records. Here we characterize this understudied Mexican ancestry. This article is part of the theme issue 'Celebrating 50 years since Lewontin's apportionment of human diversity'.

Bayesian model comparison for rare-variant association studies.

Whole-genome sequencing studies applied to large populations or biobanks with extensive phenotyping raise new analytic challenges. The need to consider many variants at a locus or group of genes simultaneously and the potential to study many correlated phenotypes with shared genetic architecture provide opportunities for discovery not addressed by the traditional one variant, one phenotype association study. Here, we introduce a Bayesian model comparison approach called MRP (multiple rare variants and phenotypes) for rare-variant association studies that considers correlation, scale, and direction of genetic effects across a group of genetic variants, phenotypes, and studies, requiring only summary statistic data. We apply our method to exome sequencing data (n = 184,698) across 2,019 traits from the UK Biobank, aggregating signals in genes. MRP demonstrates an ability to recover signals such as associations between PCSK9 and LDL cholesterol levels. We additionally find MRP effective in conducting meta-analyses in exome data. Non-biomarker findings include associations between MC1R and red hair color and skin color, IL17RA and monocyte count, and IQGAP2 and mean platelet volume. Finally, we apply MRP in a multi-phenotype setting; after clustering the 35 biomarker phenotypes based on genetic correlation estimates, we find that joint analysis of these phenotypes results in substantial power gains for gene-trait associations, such as in TNFRSF13B in one of the clusters containing diabetes- and lipid-related traits. Overall, we show that the MRP model comparison approach improves upon useful features from widely used meta-analysis approaches for rare-variant association analyses and prioritizes protective modifiers of disease risk.

Paths and timings of the peopling of Polynesia inferred from genomic networks.

Polynesia was settled in a series of extraordinary voyages across an ocean spanning one third of the Earth1, but the sequences of islands settled remain unknown and their timings disputed. Currently, several centuries separate the dates suggested by different archaeological surveys2-4. Here, using genome-wide data from merely 430 modern individuals from 21 key Pacific island populations and novel ancestry-specific computational analyses, we unravel the detailed genetic history of this vast, dispersed island network. Our reconstruction of the branching Polynesian migration sequence reveals a serial founder expansion, characterized by directional loss of variants, that originated in Samoa and spread first through the Cook Islands (Rarotonga), then to the Society (Totaiete ma) Islands (11th century), the western Austral (Tuha'a Pae) Islands and Tuamotu Archipelago (12th century), and finally to the widely separated, but genetically connected, megalithic statue-building cultures of the Marquesas (Te Henua 'Enana) Islands in the north, Raivavae in the south, and Easter Island (Rapa Nui), the easternmost of the Polynesian islands, settled in approximately AD 1200 via Mangareva.

Discovering prescription patterns in pediatric acute-onset neuropsychiatric syndrome patients.

OBJECTIVE: Pediatric acute-onset neuropsychiatric syndrome (PANS) is a complex neuropsychiatric syndrome characterized by an abrupt onset of obsessive-compulsive symptoms and/or severe eating restrictions, along with at least two concomitant debilitating cognitive, behavioral, or neurological symptoms. A wide range of pharmacological interventions along with behavioral and environmental modifications, and psychotherapies have been adopted to treat symptoms and underlying etiologies. Our goal was to develop a data-driven approach to identify treatment patterns in this cohort. MATERIALS AND METHODS: In this cohort study, we extracted medical prescription histories from electronic health records. We developed a modified dynamic programming approach to perform global alignment of those medication histories. Our approach is unique since it considers time gaps in prescription patterns as part of the similarity strategy. RESULTS: This study included 43 consecutive new-onset pre-pubertal patients who had at least 3 clinic visits. Our algorithm identified six clusters with distinct medication usage history which may represent clinician's practice of treating PANS of different severities and etiologies i.e., two most severe groups requiring high dose intravenous steroids; two arthritic or inflammatory groups requiring prolonged nonsteroidal anti-inflammatory drug (NSAID); and two mild relapsing/remitting group treated with a short course of NSAID. The psychometric scores as outcomes in each cluster generally improved within the first two years. DISCUSSION AND CONCLUSION: Our algorithm shows potential to improve our knowledge of treatment patterns in the PANS cohort, while helping clinicians understand how patients respond to a combination of drugs.